Detecting Real-World Influence Through Twitter

Abstract : In this paper, we investigate the issue of detecting the real-life influence of people based on their Twitter account. We propose an overview of common Twitter features used to characterize such accounts and their activity, and show that these are inefficient in this context. In particular, retweets and followers numbers, and Klout score are not relevant to our analysis. We thus propose several Machine Learning approaches based on Natural Language Processing and Social Network Analysis to label Twitter users as Influencers or not. We also rank them according to a predicted influence level. Our proposals are evaluated over the CLEF RepLab 2014 dataset, and outmatch state-of-the-art ranking methods.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01164453
Contributor : Vincent Labatut <>
Submitted on : Sunday, July 19, 2015 - 10:22:31 PM
Last modification on : Wednesday, July 10, 2019 - 6:17:15 PM
Long-term archiving on : Wednesday, April 26, 2017 - 7:30:19 AM

Files

enic15.pdf
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution - NonCommercial - ShareAlike 4.0 International License

Identifiers

Citation

Jean-Valère Cossu, Nicolas Dugué, Vincent Labatut. Detecting Real-World Influence Through Twitter. 2nd European Network Intelligence Conference (ENIC), Sep 2015, Karlskrona, Sweden. pp.83-90, ⟨10.1109/ENIC.2015.20⟩. ⟨hal-01164453v2⟩

Share

Metrics

Record views

454

Files downloads

227